Equipment scheduling management and control method and device of electric power system and terminal equipment

Abstract

The invention discloses an equipment dispatching management and control method and device of a power system and terminal equipment, and belongs to the field of power systems. The method comprises the following steps: extracting a first entity used for indicating the type of equipment, a second entity used for indicating scheduling operation and a third entity used for indicating a specific identifier of equipment to be scheduled from a scheduling operation instruction input by a user; taking the first entity as a retrieval starting point, and obtaining a target operation entity associated with the second entity and a target scheduling logic expression bound with the target operation entity from the power topological knowledge graph through matching; inputting the target operation entity and the target scheduling logic expression into an operation sequence generation model to obtain a target operation sequence generated by the operation sequence generation model; and according to the target operation sequence, executing a scheduling control operation on a to-be-scheduled device corresponding to the third entity. By implementing the application, the problem of low efficiency of equipment scheduling management and control links in the prior art can be solved.

Description

A method, apparatus and terminal equipment for equipment dispatching and control of a power system Technical Field

[0001] This invention relates to the field of power systems, and more particularly to a method, apparatus, and terminal equipment for equipment dispatching and control in power systems. Background Technology

[0002] As the power system continues to expand, the demands for efficient power dispatching are becoming increasingly stringent. Currently, the power industry is accelerating its intelligent transformation, but power dispatching still heavily relies on manual operation.

[0003] The current power dispatching process relies on manual interpretation of instructions, preparation of operation tickets, and execution of control measures. This is inefficient and prone to errors due to differences in personnel experience and operator fatigue. Even with some existing intelligent solutions, manual intervention is still required to complete key steps such as topology correlation. The lack of integration between power grid topology and dispatching logic results in insufficient adaptability and security of operation sequences, making it difficult to achieve a fully automated closed loop from instruction input to equipment dispatching and control. Dispatch efficiency remains significantly constrained. Summary of the Invention

[0004] This invention provides a method, apparatus, and terminal equipment for equipment dispatching and control in a power system. The method can solve the problem of low efficiency in the equipment dispatching and control process in the prior art.

[0005] To address the aforementioned technical problems, an embodiment of the present invention provides a method for equipment scheduling and control in a power system, comprising: acquiring a scheduling operation instruction input by a user; extracting from the scheduling operation instruction a first entity indicating the equipment type, a second entity indicating the scheduling operation, and a third entity indicating the specific identifier of the equipment to be scheduled; using the first entity as a retrieval starting point, matching from a power topology knowledge graph a target operation entity associated with the second entity and a target scheduling logic expression bound to the target operation entity; wherein the power topology knowledge graph includes several equipment entities and several operation entities and scheduling logic expressions bound to each equipment entity; inputting the target operation entity and the target scheduling logic expression into an operation sequence generation model to obtain a target operation sequence generated by the operation sequence generation model; wherein the operation sequence generation model is obtained by iteratively training a preset sequence generation model using several historical operation ticket samples of the power system as model input and the generated predicted operation sequence as model output; and performing scheduling and control operations on the equipment to be scheduled corresponding to the third entity according to the target operation sequence.

[0006] Furthermore, the generation process of the power topology knowledge graph includes: acquiring the original power topology data and equipment ledger data of the power system; wherein, the original power topology data includes the topology nodes and equipment type identifiers of each equipment, as well as connection lines used to indicate the connection relationships between each equipment; binding the basic operating parameters of each equipment in the equipment ledger data with the topology nodes of each equipment in the original power topology data to obtain power topology data; acquiring historical operation ticket samples corresponding to different equipment in the power system; wherein, each historical operation ticket sample includes a set of historical operation sequences and operation entities and scheduling logic expressions bound to each operation action in the historical operation sequence, with different scheduling logic expressions corresponding to different power dispatching procedures; using the topology nodes of each equipment in the power topology data as association indexes, binding each historical operation ticket sample with the corresponding topology nodes in the power topology data to generate a power topology knowledge graph; wherein, each equipment corresponds to a equipment entity in the power topology knowledge graph.

[0007] Further, the step of using the first entity as the starting point to match the target operation entity associated with the second entity and the target scheduling logic expression bound to the target operation entity from the power topology knowledge graph includes: traversing the power topology knowledge graph and filtering out equipment entities with the same equipment type as the first entity; matching the operation entities associated with the second entity along the relationship edges of each filtered equipment entity to obtain the target operation entity; and retrieving the scheduling logic expression bound to the target operation entity as the target scheduling logic expression.

[0008] Furthermore, the construction process of the operation sequence generation model includes: initializing a preset sequence generation model; taking the operation entities and corresponding scheduling logic expressions in each historical operation ticket sample as conditional inputs, taking the historical operation sequences in each historical operation ticket sample as supervision labels, taking the generated predicted operation sequences as output data, and iteratively training the sequence generation model until the loss function of the sequence generation model converges, thereby obtaining the operation sequence generation model.

[0009] Further, the step of performing scheduling and control operations on the device to be scheduled corresponding to the third entity according to the target operation sequence includes: performing a security verification on the target operation sequence to obtain a verification result of the target operation sequence; determining whether the verification result is passed; if so, performing scheduling operations on the device to be scheduled in sequence according to the target operation sequence; if not, refusing to perform scheduling operations on the device to be scheduled.

[0010] Further, the step of performing a security verification on the target operation sequence to obtain the verification result of the target operation sequence includes: simulating a power grid topology flow analysis model based on the original power topology data of the power system; inputting the target operation sequence into the power grid topology flow analysis model to simulate the power flow distribution of the power system after the operation; determining whether there is a power flow limit violation in the power flow distribution of the power system after the operation; if so, determining that the verification result of the target operation sequence is unsuccessful; otherwise, determining that the verification result of the target operation sequence is successful.

[0011] Further, the step of extracting a first entity for indicating the equipment type, a second entity for indicating the scheduling operation, and a third entity for indicating the specific identifier of the equipment to be scheduled from the scheduling operation instruction includes: inputting the scheduling operation instruction into a preset entity recognition model to obtain the first entity, the second entity, and the third entity output by the entity recognition model; wherein, the entity recognition model is based on a general language model and is obtained by performing domain adaptation fine-tuning through a labeled corpus set in the power dispatching field.

[0012] Furthermore, after performing scheduling operations on the devices to be scheduled in sequence according to the target operation sequence, the method further includes: generating a real-time operation ticket based on the target operation sequence; and synchronously pushing the real-time operation ticket and the power flow distribution of the power system to a preset scheduling and monitoring interface for visualization.

[0013] An embodiment of the present invention also provides a power system equipment dispatching and control device, comprising: an instruction acquisition module for acquiring dispatching operation instructions input by a user; an entity extraction module for extracting from the dispatching operation instructions a first entity indicating the equipment type, a second entity indicating the dispatching operation, and a third entity indicating the specific identifier of the equipment to be dispatched; a retrieval module for matching a target operation entity associated with the second entity and a target dispatching logic expression bound to the target operation entity from a power topology knowledge graph, using the first entity as the retrieval starting point; wherein the power topology knowledge graph includes a plurality of equipment entities and a plurality of operation entities and dispatching logic expressions bound to each equipment entity; an operation sequence generation module for inputting the target operation entity and the target dispatching logic expression into an operation sequence generation model to obtain a target operation sequence generated by the operation sequence generation model; wherein the operation sequence generation model is obtained by iteratively training a preset sequence generation model using a plurality of historical operation ticket samples of the power system as model input and the generated predicted operation sequence as model output; and a dispatching module for performing dispatching and control operations on the equipment to be dispatched corresponding to the third entity according to the target operation sequence.

[0014] This application also provides a terminal device, including: one or more processors; a memory coupled to the processors for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the equipment scheduling and control method of the power system as described in the above embodiments of the invention.

[0015] The present invention provides the following beneficial effects: It offers a method, apparatus, and terminal device for equipment dispatching and control in a power system. The method first parses dispatching operation instructions to extract a first entity indicating the equipment type, a second entity indicating the dispatching operation, and a third entity indicating the specific identifier of the equipment to be dispatched. This provides a clear target for subsequent operation association and execution, avoiding operational errors caused by misunderstandings of the instructions. Then, using the first entity as the starting point, it matches the target operation entity associated with the second entity and the target dispatching logic expression bound to the target operation entity from the power topology knowledge graph. Thus, the retrieved target operation entity and target dispatching logic expression provide a suitable basis for generating the operation sequence. The compliance operation guidelines and scheduling procedures for the equipment to be dispatched ensure that the subsequently generated operation process complies with power safety operation standards. Then, the target operation entity and the target scheduling logic expression are input into the operation sequence generation model to obtain the target operation sequence generated by the operation sequence generation model. Thus, the target operation sequence generated based on historical operation experience and scheduling logic constraints has process integrity and scenario adaptability. Finally, according to the target operation sequence, the dispatch control operation is performed on the equipment to be dispatched corresponding to the third entity. This effectively avoids the problems of dispatch operation relying on manual experience, non-standard operation sequences, and lack of safety verification mechanisms in the prior art, improves the automation level, compliance, and safety of power dispatch operation, and ensures the stable operation of the power grid. Attached Figure Description

[0016] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 is a flowchart illustrating a power system equipment scheduling and control method according to an embodiment of this application; Figure 2 is a structural diagram illustrating a power system equipment scheduling and control device according to an embodiment of this application; Figure 3 is a structural diagram illustrating a terminal device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0020] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0023] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0024] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0025] Referring to Figure 1, to address the problem of low efficiency in equipment scheduling and control in existing technologies, an embodiment of the present invention provides a power system equipment scheduling and control method, comprising: S1, acquiring a user-inputted scheduling operation instruction; schematically, receiving the user-inputted scheduling operation instruction, wherein the scheduling operation instruction is expressed in natural language and must include the equipment type of the equipment to be scheduled, the specific scheduling operation, and the specific identifier of the equipment to be scheduled; specifically, for example, a dispatcher inputs the instruction "execute a tripping operation on the #2 circuit breaker of the 110kV Chengdong Substation", wherein the circuit breaker is the equipment type, the tripping operation is the specific scheduling operation, and the #2 circuit breaker of the 110kV Chengdong Substation is the specific identifier of the equipment to be scheduled.

[0026] S2. Extract a first entity for indicating the device type, a second entity for indicating the scheduling operation, and a third entity for indicating the specific identifier of the device to be scheduled from the scheduling operation instruction. Schematic, in order to accurately match the associated entities and scheduling logic in the power topology knowledge graph, it is necessary to extract the above three types of entity parameters from the scheduling operation instruction, thereby providing data support for subsequent target operation entity retrieval and target operation sequence generation based on the extracted entity parameters.

[0027] In a preferred embodiment, extracting a first entity indicating the device type, a second entity indicating the scheduling operation, and a third entity indicating the specific identifier of the device to be scheduled from the scheduling operation instruction includes: inputting the scheduling operation instruction into a preset entity recognition model to obtain the first, second, and third entities output by the entity recognition model; wherein, the entity recognition model is based on a general language model and is obtained by performing domain adaptation fine-tuning using an annotated corpus in the power dispatching domain; illustratively, in order to extract entity information that fits the power dispatching scenario, it is necessary to perform domain adaptation fine-tuning on the general language model in advance; specifically, it is first necessary to collect power dispatching data... The system uses natural language dispatch instructions and standardized operation ticket texts from the power dispatch domain to form an annotated corpus for the power dispatch domain. This annotated corpus includes several dispatch instruction samples labeled with equipment type, dispatch operation, and specific equipment identifiers. The general language model is then subjected to supervised domain-specific fine-tuning training using this annotated corpus. Since many mature model fine-tuning training methods already exist, the specific training process of the entity recognition model will not be elaborated here. Specifically, after obtaining the trained entity recognition model, dispatch operation instructions need to be input into the entity recognition model so that the model can recognize and output the first, second, and third entities.

[0028] S3. Using the first entity as the starting point, match the target operation entity associated with the second entity and the target scheduling logic expression bound to the target operation entity from the power topology knowledge graph; wherein, the power topology knowledge graph includes several equipment entities and several operation entities and scheduling logic expressions bound to each equipment entity; illustratively, in order for the input of the subsequent operation sequence generation model to fit the user's input scheduling operation command and have the dual constraints of power grid topology and scheduling rules, it is necessary to match the operation entity and scheduling logic expression corresponding to the scheduling operation command from the power topology knowledge graph.

[0029] Specifically, since the first entity is used to indicate the equipment type of the equipment to be scheduled, the corresponding equipment entity in the power topology knowledge graph is associated with the first entity. Then, based on the associated equipment entity and the second entity, the operation entity associated with the two in the power topology knowledge graph and the bound scheduling logic expression are matched as the target operation entity and the target scheduling logic expression bound to the target operation entity.

[0030] Therefore, the matched target operation entity and target scheduling logic expression can be used as input features for the operation sequence generation model, providing accurate operation type guidance and scheduling logic constraints for the operation sequence generation model to generate suitable target operation sequences.

[0031] In a preferred embodiment, the generation process of the power topology knowledge graph includes: acquiring original power topology data and equipment ledger data of the power system; wherein, the original power topology data includes topology nodes and equipment type identifiers of each device, as well as connection lines indicating the connection relationships between devices; binding the basic operating parameters of each device in the equipment ledger data with the topology nodes of each device in the original power topology data to obtain power topology data; acquiring historical operation ticket samples corresponding to different devices in the power system; wherein, each historical operation ticket sample includes a set of historical operation sequences and operation entities and scheduling logic expressions bound to each operation action in the historical operation sequence, with different scheduling logic expressions corresponding to different power dispatching procedures; using the topology nodes of each device in the power topology data as association indexes, binding each historical operation ticket sample with the corresponding topology nodes in the power topology data to generate a power topology knowledge graph; wherein, each device corresponds to the power topology data... This refers to a device entity in a knowledge graph. Illustratively, the original power topology data characterizes the physical connection topology of various devices in a power system. The device ledger data includes basic operating parameters such as the model, rated power, and rated voltage of each device, supplementing the device's operating characteristic information. Specifically, by matching device identifiers, the basic operating parameters of each device in the device ledger data are bound to the topology nodes of each device in the original power topology data. Since each device's topology node possesses basic operating parameters, the generated power topology data can achieve an integrated association between device topology and operating characteristics. For example, by matching device identifiers with topology nodes, the basic operating parameters of the circuit breaker identified as "110kV Chengdong Substation #2 Circuit Breaker" in the device ledger data are bound to the corresponding topology node (node ​​ID: TB-110-02). The generated power topology data can directly associate the node's connection relationship with the device's operating parameters.

[0032] The historical operation ticket samples are illustrative, drawn from daily dispatch operation records of various equipment, including circuit breakers, disconnectors, transformers, and lines. These samples are used by dispatchers to standardize equipment operations and ensure the safe operation of the power grid. Specifically, the historical operation sequence includes the operational entity bound to each action and the dispatch logic expression. Different dispatch logic expressions correspond to different power dispatch procedures. For example, in the historical operation ticket sample for the #2 circuit breaker of the 110kV Chengdong Substation, the historical operation sequence is "Open the #2 circuit breaker of the 110kV Chengdong Substation → Open the disconnectors on both sides of the #2 circuit breaker of the 110kV Chengdong Substation → Suspend the grounding wire." The operational entity bound to the action "Open the #2 circuit breaker of the 110kV Chengdong Substation" is "circuit breaker opening operation," and the corresponding dispatch logic expression is "When the line where the circuit breaker is located has no load current and the disconnectors on both sides are closed." When in a state of emergency, a circuit breaker tripping operation can be performed (corresponding to the special regulations on circuit breaker tripping in the "Power Dispatch Section of the Power Safety Work Regulations"). Specifically, since the equipment identifiers of each device in the power topology data have been bound to the topology nodes, such as the #2 circuit breaker of the 110kV Chengdong Substation being bound to the corresponding topology node (node ​​ID: TB-110-02), when associating historical operation ticket samples with topology nodes, the equipment identifier is used as the association index to establish a one-to-one association mapping relationship between the topology nodes and the corresponding historical operation ticket samples. Through this association method, each topology node in the generated power topology knowledge graph contains not only the equipment topology connection relationship and basic operating parameters, but also compliant operation actions and corresponding dispatching logic rules, providing data support for subsequently retrieving the target operation entity and dispatching logic expression from the power topology knowledge graph.

[0033] The completed power topology knowledge graph includes several device entities and operation entities, and the entities are associated with each other through relation edges (derived from the connection lines used to indicate the connection relationships between devices). Among them, device entities are bound to basic operating parameters, device identifiers and topology node information, while operation entities are bound to corresponding scheduling logic expressions one by one. Furthermore, operation entities are associated with adapted device entities to ensure that each type of device entity is only associated with operation entities and scheduling logic expressions within its compliant scope.

[0034] In a preferred embodiment, the step of using the first entity as the starting point to match the target operation entity associated with the second entity and the target scheduling logic expression bound to the target operation entity from the power topology knowledge graph includes: traversing the power topology knowledge graph and filtering out device entities of the same type as the first entity; matching the operation entities associated with the second entity along the relation edges of each filtered device entity to obtain the target operation entity; and retrieving the scheduling logic expression bound to the target operation entity as the target scheduling logic expression. Specifically, in order to filter out device entities of the same type as the device to be scheduled and provide more compliant operation references for the subsequent operation sequence generation model, it is necessary to traverse the power topology knowledge graph using a graph traversal algorithm to filter out device entities of the same type as the first entity. For example, if the first entity is a "circuit breaker", then after traversing the knowledge graph, all device entities identified as "circuit breaker" are filtered out.

[0035] Specifically, each device entity in the power topology knowledge graph is pre-bound to its corresponding operation entity. Therefore, by matching the relationship edges of each selected device entity, the operation entity associated with the second entity is obtained, thus obtaining the target operation entity. For example, if the second entity is "circuit breaker tripping operation", then by matching the relationship edges of all selected circuit breaker device entities, the operation entity marked "circuit breaker tripping operation" is obtained, and "circuit breaker tripping operation" is taken as the target operation entity. Then, the scheduling logic expression bound to the target operation entity is retrieved as the target scheduling logic expression.

[0036] S4. Input the target operation entity and the target scheduling logic expression into the operation sequence generation model to obtain the target operation sequence generated by the operation sequence generation model; wherein, the operation sequence generation model is obtained by iteratively training a preset sequence generation model with several historical operation ticket samples of the power system as model input and the generated predicted operation sequence as model output; illustratively, after completing the entity extraction of scheduling operation instructions and the matching and retrieval of target operation entities and scheduling logic expressions in steps S1-S3, the selected target operation entities and target scheduling logic expressions provide clear operation type guidance and scheduling logic constraints for operation sequence generation. Therefore, the target operation entity and the target scheduling logic expression are input into the operation sequence generation model, and the operation sequence generation model, combined with the operation process rules of the historical operation ticket samples learned in the training phase, generates a target operation sequence that conforms to the power dispatching regulations and is adapted to the actual working conditions of the equipment to be dispatched.

[0037] In a preferred embodiment, the construction process of the operation sequence generation model includes: initializing a preset sequence generation model; taking the operation entities and corresponding scheduling logic expressions in each historical operation ticket sample as conditional inputs, the historical operation sequences in each historical operation ticket sample as supervision labels, and the generated predicted operation sequences as output data, iteratively training the sequence generation model until the loss function of the sequence generation model converges, thereby obtaining the operation sequence generation model; illustratively, the sequence generation model can be a sequence modeling model such as Transformer or LSTM, which already has basic sequence feature extraction and sequence generation capabilities. However, since general sequence generation models are not adapted to the operation logic and procedural requirements of the power dispatching field, it is necessary to perform supervised iterative training on the preset sequence generation model in the power dispatching field to obtain an operation sequence generation model that fits the actual operation scenario of power dispatching.

[0038] Specifically, the operation entities and corresponding scheduling logic expressions in each historical operation ticket sample are used as input conditions to give the model explicit operation type constraints and scheduling logic rule constraints, avoiding the generation of irregular operation sequences. The historical operation sequences in each historical operation ticket sample are used as supervision labels, allowing the model to learn from compliant historical operation procedures and continuously calibrate the generation accuracy of predicted operation sequences. The generated predicted operation sequences are used as output data to iteratively train the sequence generation model until the loss function of the sequence generation model converges, thus obtaining the operation sequence generation model. This ensures that the operation sequences generated by the model comply with the requirements of power dispatching regulations and have process integrity and logical rationality.

[0039] It should be noted that since the iterative training method and loss function convergence criterion of the sequence generation model are existing mature technologies, and the relevant training process can be implemented through conventional machine learning training frameworks, the specific training details of the sequence generation model will not be elaborated here.

[0040] S5. According to the target operation sequence, perform scheduling and control operations on the device to be scheduled corresponding to the third entity; illustratively, after generating the target operation sequence in step S4, scheduling and control operations can be performed on the device to be scheduled mentioned in the scheduling operation instruction input by the user.

[0041] In a preferred embodiment, the step of performing scheduling and control operations on the device to be scheduled corresponding to the third entity according to the target operation sequence includes: performing a security verification on the target operation sequence to obtain a verification result of the target operation sequence; determining whether the verification result is passed; if so, performing scheduling operations on the device to be scheduled sequentially according to the target operation sequence; if not, refusing to perform scheduling operations on the device to be scheduled. This is illustratively, to avoid power grid operation safety risks caused by scheduling operations, it is necessary to first perform a security verification on the target operation sequence to obtain a verification result, thereby ensuring the security and feasibility of the scheduling operation. Specifically, after determining that the verification result is passed, the scheduling operation is performed on the device to be scheduled sequentially according to the target operation sequence, i.e., based on the information provided in the scheduling operation instruction... The obtained third entity (the specific identifier of the equipment to be dispatched) is used to select the corresponding equipment to be dispatched, locate its topology node in the power topology knowledge graph, and retrieve the basic operating parameters and real-time operating status of the equipment to be dispatched. Then, based on the basic operating parameters and real-time operating status, the dispatching operation is executed sequentially according to each operation step in the target operation sequence. For example, if the target operation sequence is "open the #2 circuit breaker of 110kV Chengdong Substation → open the disconnect switches on both sides → hang the grounding wire", then first locate the topology node corresponding to the circuit breaker, retrieve its load current, switch status and other parameters, and then execute the dispatching operations of opening the circuit breaker, opening the disconnect switch and hanging the grounding wire in sequence. If the verification result is not passed, the dispatching operation on the equipment to be dispatched is refused, thereby realizing the safe control of the dispatching of the equipment to be dispatched and avoiding power grid equipment failure from the source of operation.

[0042] In a preferred embodiment, the step of performing a security verification on the target operation sequence to obtain a verification result includes: simulating a power grid topology flow analysis model based on the original power topology data of the power system; inputting the target operation sequence into the power grid topology flow analysis model to simulate the power flow distribution of the power system after the operation; determining whether there is a power flow limit violation in the power flow distribution of the power system after the operation; if so, determining that the verification result of the target operation sequence is failed; if not, determining that the verification result of the target operation sequence is passed. This embodiment, illustratively, uses power grid flow simulation analysis to perform a security verification on the target operation sequence, thereby judging the execution feasibility and security of the target operation sequence based on the actual power flow distribution state of the power grid after the operation.

[0043] Specifically, based on the original power topology data of the power system, the power flow modeling and simulation calculation function of the cloud simulation platform is invoked to simulate a power flow analysis model that conforms to the actual topology of the power system. Then, the target operation sequence is input into the power flow analysis model. The power flow analysis model simulates the changes in electrical quantities such as voltage, branch power, and line current of each node in the power system after the operation of the equipment based on the target operation sequence, and outputs the power flow distribution of the power system after the operation. Then, the cloud simulation platform compares the simulated values ​​of each electrical quantity after the operation with the rated threshold and safe operation threshold specified in the power dispatching regulations to determine whether there is a power flow exceeding the limit in the power flow distribution of the power system after the operation. If so, the verification result of the target operation sequence is determined to be unsuccessful; otherwise, the verification result of the target operation sequence is determined to be successful.

[0044] In a preferred embodiment, after performing scheduling operations on the equipment to be scheduled in sequence according to the target operation sequence, the method further includes: generating a real-time operation ticket based on the target operation sequence; and simultaneously pushing the real-time operation ticket and the power flow distribution of the power system to a preset scheduling monitoring interface for visualization. Specifically, the operation ticket is a compliance certificate that records the scheduling operation process, clarifies the operation content and safety precautions, and dispatchers need to keep track of the operation execution status in real time, retain operation records for filing, and monitor the power grid operation status after the operation. Therefore, after performing scheduling operations on the equipment to be scheduled, it is necessary to automatically generate a standardized real-time operation ticket based on the complete steps of the target operation sequence (including each operation action, execution sequence, and compliance basis), and simultaneously retrieve the power flow distribution data of the power system after the operation, and push both to the preset scheduling monitoring interface. The operation ticket details and power flow changes are displayed intuitively in a graphical and visual manner, which facilitates dispatchers to check the operation compliance and monitor the stability of power grid operation in real time.

[0045] Referring to Figure 2, an embodiment of the present invention provides a power system equipment dispatching and control device, comprising: an instruction acquisition module for acquiring dispatching operation instructions input by a user; an entity extraction module for extracting from the dispatching operation instructions a first entity indicating the equipment type, a second entity indicating the dispatching operation, and a third entity indicating the specific identifier of the equipment to be dispatched; a retrieval module for matching a target operation entity associated with the second entity and a target dispatching logic expression bound to the target operation entity from a power topology knowledge graph, using the first entity as the retrieval starting point; wherein the power topology knowledge graph includes several equipment entities and several operation entities and dispatching logic expressions bound to each equipment entity; an operation sequence generation module for inputting the target operation entity and the target dispatching logic expression into an operation sequence generation model to obtain a target operation sequence generated by the operation sequence generation model; wherein the operation sequence generation model is obtained by iteratively training a preset sequence generation model using several historical operation ticket samples of the power system as model input and the generated predicted operation sequence as model output; and a dispatching module for performing dispatching and control operations on the equipment to be dispatched corresponding to the third entity according to the target operation sequence.

[0046] Referring to Figure 3, one embodiment of this application also provides a terminal device, including: one or more processors; a memory coupled to the processors for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the equipment scheduling and control method of the power system as described above.

[0047] The processor controls the overall operation of the terminal device to complete all or part of the steps of the aforementioned power system equipment scheduling and control method. The memory stores various types of data to support the operation of the terminal device. This data may include, for example, instructions for any application or method used to operate on the terminal device, as well as application-related data. The memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0048] In an exemplary embodiment, the terminal device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the power system equipment scheduling and control method as described in any of the above embodiments, and achieve the same technical effects as the above methods.

[0049] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for equipment dispatching and control in a power system, characterized in that, include: Obtain the scheduling operation instructions input by the user; The scheduling operation instructions extract a first entity indicating the equipment type, a second entity indicating the scheduling operation, and a third entity indicating the specific identifier of the equipment to be scheduled. Using the first entity as the starting point, a target operation entity associated with the second entity and a target scheduling logic expression bound to the target operation entity are matched from the power topology knowledge graph. The power topology knowledge graph includes several equipment entities and several operation entities and scheduling logic expressions bound to each equipment entity. The target operation entity and the target scheduling logic expression are input into an operation sequence generation model to obtain a target operation sequence generated by the operation sequence generation model. The operation sequence generation model is obtained by iteratively training a preset sequence generation model using several historical operation ticket samples from the power system as model input and the generated predicted operation sequence as model output. Based on the target operation sequence, a scheduling control operation is performed on the equipment to be scheduled corresponding to the third entity.

2. The power system equipment dispatching and control method as described in claim 1, characterized in that, The generation process of the power topology knowledge graph includes: acquiring the original power topology data and equipment ledger data of the power system; wherein, the original power topology data includes the topology nodes and equipment type identifiers of each equipment, as well as connection lines used to indicate the connection relationships between each equipment; binding the basic operating parameters of each equipment in the equipment ledger data with the topology nodes of each equipment in the original power topology data to obtain power topology data; acquiring historical operation ticket samples corresponding to different equipment in the power system; wherein, each historical operation ticket sample includes a set of historical operation sequences and operation entities and scheduling logic expressions bound to each operation action in the historical operation sequence, with different scheduling logic expressions corresponding to different power dispatching procedures; using the topology nodes of each equipment in the power topology data as association indexes, binding each historical operation ticket sample with the corresponding topology nodes in the power topology data to generate a power topology knowledge graph; wherein, each equipment corresponds to a equipment entity in the power topology knowledge graph.

3. The power system equipment dispatching and control method as described in claim 2, characterized in that, The step of using the first entity as the starting point to match the target operation entity associated with the second entity and the target scheduling logic expression bound to the target operation entity from the power topology knowledge graph includes: traversing the power topology knowledge graph and filtering out equipment entities with the same equipment type as the first entity; matching the operation entities associated with the second entity along the relationship edges of each filtered equipment entity to obtain the target operation entity; and retrieving the scheduling logic expression bound to the target operation entity as the target scheduling logic expression.

4. The power system equipment dispatching and control method as described in claim 2, characterized in that, The process of constructing the operation sequence generation model includes: initializing a preset sequence generation model; taking the operation entities and corresponding scheduling logic expressions in each historical operation ticket sample as conditional inputs, taking the historical operation sequences in each historical operation ticket sample as supervision labels, taking the generated predicted operation sequences as output data, and iteratively training the sequence generation model until the loss function of the sequence generation model converges, thereby obtaining the operation sequence generation model.

5. The power system equipment dispatching and control method as described in claim 2, characterized in that, The step of performing scheduling and control operations on the device to be scheduled corresponding to the third entity according to the target operation sequence includes: performing a security verification on the target operation sequence to obtain a verification result of the target operation sequence; determining whether the verification result is passed; if so, performing scheduling operations on the device to be scheduled in sequence according to the target operation sequence; if not, refusing to perform scheduling operations on the device to be scheduled.

6. The equipment dispatching and control method for a power system as described in claim 2, characterized in that, The step of performing a security verification on the target operation sequence to obtain the verification result of the target operation sequence includes: simulating a power grid topology flow analysis model based on the original power topology data of the power system; inputting the target operation sequence into the power grid topology flow analysis model to simulate the power flow distribution of the power system after the operation; determining whether there is a power flow limit violation in the power flow distribution of the power system after the operation; if so, determining that the verification result of the target operation sequence is unsuccessful; otherwise, determining that the verification result of the target operation sequence is successful.

7. The power system equipment dispatching and control method as described in claim 1, characterized in that, The step of extracting a first entity for indicating the equipment type, a second entity for indicating the scheduling operation, and a third entity for indicating the specific identifier of the equipment to be scheduled from the scheduling operation instruction includes: inputting the scheduling operation instruction into a preset entity recognition model to obtain the first entity, the second entity, and the third entity output by the entity recognition model; wherein, the entity recognition model is based on a general language model and is obtained by performing domain adaptation fine-tuning through a labeled corpus set in the power dispatching field.

8. The power system equipment dispatching and control method as described in claim 5, characterized in that, After performing scheduling operations on the devices to be scheduled in sequence according to the target operation sequence, the method further includes: generating a real-time operation ticket based on the target operation sequence; and synchronously pushing the real-time operation ticket and the power flow distribution of the power system to a preset scheduling and monitoring interface for visualization.

9. A power system equipment dispatching and control device, characterized in that, include: The instruction acquisition module is used to acquire the scheduling operation instructions input by the user; An entity extraction module is used to extract a first entity indicating the equipment type, a second entity indicating the scheduling operation, and a third entity indicating the specific identifier of the equipment to be scheduled from the scheduling operation instruction. A retrieval module is used to match the target operation entity associated with the second entity and the target scheduling logic expression bound to the target operation entity from the power topology knowledge graph, starting from the first entity. The power topology knowledge graph includes several equipment entities and several operation entities and scheduling logic expressions bound to each equipment entity. An operation sequence generation module is used to input the target operation entity and the target scheduling logic expression into an operation sequence generation model to obtain a target operation sequence generated by the operation sequence generation model. The operation sequence generation model is obtained by iteratively training a preset sequence generation model with several historical operation ticket samples of the power system as model input and the generated predicted operation sequence as model output. A scheduling module is used to perform scheduling and control operations on the equipment to be scheduled corresponding to the third entity according to the target operation sequence.

10. A terminal device, characterized in that, include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the equipment scheduling and control method for a power system as described in any one of claims 1-8.

Images